Pricing

Free to use. Pay for what you run.

MindsHub Agents and MindsHub Inference use the same rate card. There is no subscription or plan.

Free The MindsHub Air model and Jev, free within fair use. No card.
Your keys Any model on your own provider accounts — you pay them, not us.
Credits Everything else, at the published rates below.

Free tier

Use the included models at no charge with your MindsHub account.

$0 No credit card required

Included models

MindsHub Air model

A general-purpose model for everyday work with agents.

Use in MindsHub Agents or through MindsHub Inference.

API alias mindshub_air Use Air with the API →

Jev

TypeSafe’s decision model for classification, routing and scoring.

Get choices, scores and probabilities through the Decisions API.

API alias jev Jev API guide →

Rate card

Model rates.

Prices are in US dollars per million tokens. Expand a row for long-prompt rates, web search, cache writes, reasoning levels, and failover order.

Compare models

Model	Provider	Input	Output	Cached input	Cache write
Free tier — fair use applies	MindsHub	$0.20	$1.20	$0.02	$0.25
Free tier Free within fair use, in MindsHub Agents and through the API. Daily limits apply. The rates here are Air's list rates for usage outside the free tier. Air is an alias we keep pointed at the model that strikes the best balance of cost, speed and intelligence, so both the target and these rates can move as better options ship. Long prompts — 272K+ tokens $0.40 input $1.80 output $0.04 cached input $0.50 cache write Per 1M tokens. Once a prompt crosses 272K tokens, these rates replace the standard ones for the whole request — the same way MindsHub bills it. Web search $10.00 per 1,000 searches MindsHub's own search, built into the model. Failover order Gemini Flash Tried in this order if MindsHub Air is unavailable, so your work keeps moving.
	Cerebras	$0.99	$1.49	$0.99	Free
Long prompts No surcharge — the full context window bills at the standard rates above. Cache writes Free on this model — you're billed only when cached content is read back, at the cached-input rate above. Reasoning effort `nonehigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order GPT-OSS 120B (Fireworks) Tried in this order if MindsHub Blaze is unavailable, so your work keeps moving.
	Fireworks AI	$0.15	$0.60	$0.02	$0.15
Long prompts No surcharge — the full context window bills at the standard rates above. Failover order No backup configured for this model.
	Anthropic	$2.00	$10.00	$0.20	$2.50
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $10.00 per 1,000 searches Anthropic's own search, built into the model. Reasoning effort `lowmediumhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order GPT Tried in this order if Claude Sonnet 5 is unavailable, so your work keeps moving.
	Anthropic	$4.00	$20.00	$0.20	$5.00
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $10.00 per 1,000 searches Anthropic's own search, built into the model. Reasoning effort `lowmediumhighxhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order GPT Tried in this order if Claude Opus 5.5 is unavailable, so your work keeps moving.
	Anthropic	$5.00	$25.00	$0.50	$6.25
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $10.00 per 1,000 searches Anthropic's own search, built into the model. Reasoning effort `lowmediumhighxhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order GPT Tried in this order if Claude Opus 5 is unavailable, so your work keeps moving.
	Anthropic	$10.00	$50.00	$0.25	$12.50
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $10.00 per 1,000 searches Anthropic's own search, built into the model. Reasoning effort `lowmediumhighxhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order GPT Tried in this order if Claude Fable 5.1 is unavailable, so your work keeps moving.
	Anthropic	$10.00	$50.00	$1.00	$12.50
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $10.00 per 1,000 searches Anthropic's own search, built into the model. Reasoning effort `lowmediumhighxhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order GPT Tried in this order if Claude Fable 5 is unavailable, so your work keeps moving.
	Anthropic	$1.00	$5.00	$0.10	$1.25
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $10.00 per 1,000 searches Anthropic's own search, built into the model. Failover order Gemini Flash DeepSeek Flash Tried in this order if Claude Haiku 4.5 is unavailable, so your work keeps moving.
	OpenAI	$10.00	$50.00	$1.00	$12.50
Long prompts — 272K+ tokens $20.00 input $75.00 output $2.00 cached input $25.00 cache write Per 1M tokens. Once a prompt crosses 272K tokens, these rates replace the standard ones for the whole request — the same way OpenAI bills it. Web search $10.00 per 1,000 searches OpenAI's own search, built into the model. Reasoning effort `lowmediumhighxhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send medium unless you ask for another. Failover order Claude Opus Gemini Pro Tried in this order if GPT-6 Astra is unavailable, so your work keeps moving.
	OpenAI	$5.00	$30.00	$0.50	$6.25
Long prompts — 272K+ tokens $10.00 input $45.00 output $1.00 cached input $12.50 cache write Per 1M tokens. Once a prompt crosses 272K tokens, these rates replace the standard ones for the whole request — the same way OpenAI bills it. Web search $10.00 per 1,000 searches OpenAI's own search, built into the model. Reasoning effort `nonelowmediumhighxhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send medium unless you ask for another. Failover order Claude Opus Gemini Pro Tried in this order if GPT 5.6 Sol is unavailable, so your work keeps moving.
	OpenAI	$2.00	$10.00	$0.20	$2.50
Long prompts — 272K+ tokens $4.00 input $15.00 output $0.40 cached input $5.00 cache write Per 1M tokens. Once a prompt crosses 272K tokens, these rates replace the standard ones for the whole request — the same way OpenAI bills it. Web search $10.00 per 1,000 searches OpenAI's own search, built into the model. Reasoning effort `nonelowmediumhighxhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send medium unless you ask for another. Failover order Claude Opus Gemini Pro Tried in this order if GPT-6 Sol is unavailable, so your work keeps moving.
	OpenAI	$2.00	$12.00	$0.20	$2.50
Long prompts — 272K+ tokens $4.00 input $18.00 output $0.40 cached input $5.00 cache write Per 1M tokens. Once a prompt crosses 272K tokens, these rates replace the standard ones for the whole request — the same way OpenAI bills it. Web search $10.00 per 1,000 searches OpenAI's own search, built into the model. Reasoning effort `nonelowmediumhighxhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send medium unless you ask for another. Failover order Claude Sonnet Gemini Pro Tried in this order if GPT 5.6 Terra is unavailable, so your work keeps moving.
	OpenAI	$0.10	$0.50	$0.01	$0.125
Long prompts — 272K+ tokens $0.20 input $0.75 output $0.02 cached input $0.25 cache write Per 1M tokens. Once a prompt crosses 272K tokens, these rates replace the standard ones for the whole request — the same way OpenAI bills it. Web search $10.00 per 1,000 searches OpenAI's own search, built into the model. Reasoning effort `nonelowmediumhighxhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send medium unless you ask for another. Failover order Gemini Flash Claude Haiku Tried in this order if GPT-6 Luna is unavailable, so your work keeps moving.
	OpenAI	$0.20	$1.20	$0.02	$0.25
Long prompts — 272K+ tokens $0.40 input $1.80 output $0.04 cached input $0.50 cache write Per 1M tokens. Once a prompt crosses 272K tokens, these rates replace the standard ones for the whole request — the same way OpenAI bills it. Web search $10.00 per 1,000 searches OpenAI's own search, built into the model. Reasoning effort `nonelowmediumhighxhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send medium unless you ask for another. Failover order Gemini Flash Claude Haiku Tried in this order if GPT 5.6 Luna is unavailable, so your work keeps moving.
	OpenAI	$1.75	$14.00	$0.18	$1.75
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $10.00 per 1,000 searches OpenAI's own search, built into the model. Reasoning effort `lowmediumhighxhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send medium unless you ask for another. Failover order Claude Sonnet Tried in this order if GPT 5.3 Codex is unavailable, so your work keeps moving.
	OpenAI	$0.75	$4.50	$0.08	$0.75
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $10.00 per 1,000 searches OpenAI's own search, built into the model. Reasoning effort `nonelowmediumhighxhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send none unless you ask for another. Failover order Gemini Flash Claude Haiku Tried in this order if GPT 5.4 Mini is unavailable, so your work keeps moving.
	OpenAI	$0.20	$1.25	$0.02	$0.20
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $10.00 per 1,000 searches OpenAI's own search, built into the model. Reasoning effort `nonelowmediumhighxhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send none unless you ask for another. Failover order Gemini Flash Tried in this order if GPT 5.4 Nano is unavailable, so your work keeps moving.
	Google	$2.00	$12.00	$0.20	Free
Long prompts — 200K+ tokens $4.00 input $18.00 output $0.40 cached input Per 1M tokens. Once a prompt crosses 200K tokens, these rates replace the standard ones for the whole request — the same way Google bills it. Web search $14.00 per 1,000 searches Google's own search, built into the model. Cache writes Free on this model — you're billed only when cached content is read back, at the cached-input rate above. Reasoning effort `lowmediumhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order Claude Sonnet GPT Tried in this order if Gemini 3.1 Pro Preview is unavailable, so your work keeps moving.
	Google	$0.75	$3.75	$0.08	Free
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $14.00 per 1,000 searches Google's own search, built into the model. Cache writes Free on this model — you're billed only when cached content is read back, at the cached-input rate above. Reasoning effort `lowmediumhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send medium unless you ask for another. Failover order GPT Mini DeepSeek Flash Tried in this order if Gemini 3.8 Flash is unavailable, so your work keeps moving.
	Google	$0.75	$3.75	$0.08	Free
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $14.00 per 1,000 searches Google's own search, built into the model. Cache writes Free on this model — you're billed only when cached content is read back, at the cached-input rate above. Reasoning effort `lowmediumhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send medium unless you ask for another. Failover order GPT Mini DeepSeek Flash Tried in this order if Gemini 3.7 Flash is unavailable, so your work keeps moving.
	Google	$0.75	$3.75	$0.08	Free
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $14.00 per 1,000 searches Google's own search, built into the model. Cache writes Free on this model — you're billed only when cached content is read back, at the cached-input rate above. Reasoning effort `minimallowmediumhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send medium unless you ask for another. Failover order GPT Mini DeepSeek Flash Tried in this order if Gemini 3.6 Flash is unavailable, so your work keeps moving.
	Google	$1.50	$9.00	$0.15	Free
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $14.00 per 1,000 searches Google's own search, built into the model. Cache writes Free on this model — you're billed only when cached content is read back, at the cached-input rate above. Reasoning effort `minimallowmediumhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send medium unless you ask for another. Failover order GPT Mini DeepSeek Flash Tried in this order if Gemini 3.5 Flash is unavailable, so your work keeps moving.
	Google	$0.50	$3.00	$0.05	Free
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $14.00 per 1,000 searches Google's own search, built into the model. Cache writes Free on this model — you're billed only when cached content is read back, at the cached-input rate above. Reasoning effort `minimallowmediumhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order GPT Mini DeepSeek Flash Tried in this order if Gemini 3 Flash Preview is unavailable, so your work keeps moving.
	Google	$0.25	$1.50	$0.03	Free
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $14.00 per 1,000 searches Google's own search, built into the model. Cache writes Free on this model — you're billed only when cached content is read back, at the cached-input rate above. Reasoning effort `minimallowmediumhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send minimal unless you ask for another. Failover order GPT Nano DeepSeek Flash Tried in this order if Gemini 3.1 Flash-Lite is unavailable, so your work keeps moving.
	Fireworks AI	$3.00	$15.00	$0.30	$3.00
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately. Failover order DeepSeek Flash Tried in this order if Kimi K3 is unavailable, so your work keeps moving.
	Fireworks AI	$0.22	$0.66	$0.01	$0.22
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately. Reasoning effort `nonelowhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order GLM Flash Tried in this order if DeepSeek V4.1 Flash is unavailable, so your work keeps moving.
	Fireworks AI	$2.00	$6.00	$0.25	$2.00
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately. Reasoning effort `lowmediumxhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send xhigh unless you ask for another. Failover order DeepSeek Flash Tried in this order if Qwen3.8-2.4T-A95B is unavailable, so your work keeps moving.
	Fireworks AI	$1.40	$4.40	$0.26	$1.40
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately. Reasoning effort `lowhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send max unless you ask for another. Failover order DeepSeek Flash Tried in this order if GLM 5.3 is unavailable, so your work keeps moving.
	Fireworks AI	$1.40	$4.40	$0.14	$1.40
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately. Reasoning effort `highmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send max unless you ask for another. Failover order DeepSeek Flash Tried in this order if GLM 5.2 is unavailable, so your work keeps moving.
	Fireworks AI	$0.15	$0.50	$0.03	$0.15
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately. Reasoning effort `lowhighmax` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send max unless you ask for another. Failover order DeepSeek Flash Tried in this order if GLM 5.3 Flash is unavailable, so your work keeps moving.
	Meta	$1.25	$4.25	$0.15	$1.25
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately. Failover order Claude Sonnet Kimi Tried in this order if Muse Spark 1.3 is unavailable, so your work keeps moving.
	Meta	$1.25	$4.25	$0.15	$1.25
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately. Failover order Claude Sonnet Kimi Tried in this order if Muse Spark 1.2 is unavailable, so your work keeps moving.
	Meta	$1.25	$4.25	$0.15	$1.25
Long prompts No surcharge — the full context window bills at the standard rates above. Web search $7.00 per 1,000 searches $1.00 per 1,000 page fetches Served by Exa, which bills page fetches separately. Failover order Claude Sonnet Kimi Tried in this order if Muse Spark 1.1 is unavailable, so your work keeps moving.
	SpaceXAI	$2.00	$6.00	$0.50	$2.00
Long prompts — 200K+ tokens $4.00 input $12.00 output $1.00 cached input $4.00 cache write Per 1M tokens. Once a prompt crosses 200K tokens, these rates replace the standard ones for the whole request — the same way SpaceXAI bills it. Web search $5.00 per 1,000 searches SpaceXAI's own search, built into the model. Reasoning effort `lowmediumhighxhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order Claude Sonnet Kimi Tried in this order if Grok 4.7 is unavailable, so your work keeps moving.
	SpaceXAI	$2.00	$6.00	$0.50	$2.00
Long prompts — 200K+ tokens $4.00 input $12.00 output $1.00 cached input $4.00 cache write Per 1M tokens. Once a prompt crosses 200K tokens, these rates replace the standard ones for the whole request — the same way SpaceXAI bills it. Web search $5.00 per 1,000 searches SpaceXAI's own search, built into the model. Reasoning effort `lowmediumhighxhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order Claude Sonnet Kimi Tried in this order if Grok 4.6 is unavailable, so your work keeps moving.
	SpaceXAI	$2.00	$6.00	$0.30	$2.00
Long prompts — 200K+ tokens $4.00 input $12.00 output $0.60 cached input $4.00 cache write Per 1M tokens. Once a prompt crosses 200K tokens, these rates replace the standard ones for the whole request — the same way SpaceXAI bills it. Web search $5.00 per 1,000 searches SpaceXAI's own search, built into the model. Reasoning effort `lowmediumhigh` Dial thinking up or down per task. Higher effort spends more output tokens, billed at the same rate. We send high unless you ask for another. Failover order Claude Sonnet Kimi Tried in this order if Grok 4.5 is unavailable, so your work keeps moving.

Units: Token prices are USD per 1M tokens. Web search and page fetches are USD per 1,000 calls.
Cached input: The discounted rate for prompt content the provider already has cached.
Cache write: What it costs to put content into that cache in the first place.
More per model: Expand any row for its long-prompt rates, search pricing and failover order.

MindsHub Foundry

Double your first 3 months of credit.

Selected teams test new features with our product team and receive a 100% match on inference-credit purchases for three months, up to $5,000.

About the Foundry

The MindsHub Agents workspace runs in your browser and in the desktop app — the same workspace either way. Get the app for macOS, Windows or Linux.

Ask questions and share ideas in the community Discord, or send a private support request about a specific issue.

FAQ

Common questions.

What does it cost to start?

Nothing. The MindsHub Air model and TypeSafe’s Jev decision model are included in the free tier, subject to fair use. No card is needed.

How do I use paid models?

Add credits and pay the published per-model rate. You can top up manually or use auto-recharge with a monthly cap.

Can I use my own provider API keys instead?

Yes. Add your provider keys and pay the provider directly.

Is there a subscription or a minimum?

No. There is no subscription, monthly fee, or minimum spend. You pay only for hosted usage outside the free tier, or use your own keys.

What is MindsHub Air?

MindsHub Air is a model alias: we keep it pointed at a balanced model and can move it as the catalog changes. It is included in the free tier: anyone with a MindsHub account can use it at no charge within fair use. Air does not support web search or reasoning-effort controls.

Where can I use the free tier?

Use the MindsHub Air model in MindsHub Agents, or through MindsHub Inference as mindshub_air from an agent or your own code. Use Jev through the Decisions API with the alias jev and your MindsHub key. The fair-use policy applies to both models.

What does fair use mean?

The free tier is for people using agents. Daily rate limits and other measures protect it; the limits are not published as numbers. Extensive automated machine use, for example bulk pipelines, scripted volume traffic, scraping or resale, is not covered, and accounts used that way can be suspended. The policy is at mindshub.ai/fair-use-policy.

What if a limit stops me by mistake?

The system will not always get it right. If a daily limit or a suspension stops you and you think that's a mistake, contact us at mindshub.ai/contact with your account email, what you were doing, and when.

Do MindsHub Agents and the API share this pricing?

Yes. Both use the same rate card and prepaid balance.

Which models are available?

The catalog includes MindsHub Air, Claude, GPT, Gemini, Grok, Muse Spark, Kimi, DeepSeek, Qwen, and GLM families. Check the live rate card for current versions, prices, and failover order.

Can I see what a task cost?

Yes. Your account shows usage, and the rate card lists each model price.

How do I get support?

Ask the team and community in Discord, or submit a private support request at mindshub.ai/support for a specific issue.

Can I pay with cryptocurrency?

Standard top-ups use a card. Volume customers can ask the team about settling invoices in cryptocurrency.

How do models stay current?

Family aliases can move to newer model versions. The rate card shows the fallback order for each model that has one.

What is MindsHub?

MindsHub includes MindsHub Agents, the agent workspace, and MindsHub Inference, the API. They share one model catalog and balance.

Can I run MindsHub myself?

Yes. You can run the open-source project on your computer or in your VPC with your own endpoints and keys. This page prices the hosted service.

Which open-source agent harness powers MindsHub Agents?

MindsHub Agents runs on Anton, an open-source agent harness. Switching models does not remove your workspace data.